Frequency-aware Deep Dual-path Feature Enhancement Network for Image Dehazing

Single image dehazing is a challenging task due to the severe degradations caused by the particles in the air. Recently, various CNN-based methods have been proposed and they have achieved promising results on some dehazing tasks. However, the existing end-to-end dehazing networks process high-frequency information and low-frequency information at the same time. Therefore, most dehazing methods cannot restore dehazed image with satisfying high-frequency details. In this paper, we propose a Frequency-aware deep Dual-path Feature enhancement Network (FDF-Net) to better restore the high-frequency information while removing the haze. To achieve this, we introduce a Dual-path Feature Enhancement (DFE) block, which contains two branches: one path is to remedy the missing spatial information from high-resolution features, and the other one is to obtain new features to increase the variety of features. We believe the dual-path architecture can help the first path to focus on the recovering the high-frequency information. Furthermore, to reserve more detailed image information from the features with larger resolution, we adopt a wavelet transform module during the downsampling process of the encoder module to directly pass the high frequency information to the next level. The extensive experiments show the superiority of the proposed model over previous methods on the benchmark datasets as well as real-world hazy images.

I. Introduction

During the imaging process, the haze is an important factor that causes the decline in the visual quality of the object appearance and contrast. The goal of image dehazing is to restore clear images from hazy images. This task is of great significance because image dehazing can pave the way for the subsequent high-level vision tasks, such as segmentation [1], scene understanding [2] and object detection [3]. The atmospheric scattering model [4], [5] provides a simple approximation of the haze effect, which is expressed as:

$$\begin{equation*}I(x) = T(x)J(x) + (1 - T(x))A\tag{1}\end{equation*}$$ where I(x) represents the observed hazy image, A describes the global atmospheric light indicating the intensity of ambient light, T (x) is the medium transmission map, J(x) denotes the haze-free scene radiance, and x is the pixel position.